Machine Learning Blog | ML@CMU | Carnegie Mellon University blog.ml.cmu.edu

Carnegie Mellon at NeurIPS 2025

blog.ml.cmu.edu·3d

Yes, AI, There is a Santa Claus

blog.ml.cmu.edu·7w

Validating LLM-as-a-Judge Systems under Rating Indeterminacy

blog.ml.cmu.edu·9w

Carnegie Mellon at NeurIPS 2025

blog.ml.cmu.edu·10w

How to Explore to Scale RL Training of LLMs on Hard Problems? – Machine Learning Blog | ML@CMU | Carnegie Mellon University

blog.ml.cmu.edu·11w

How to Explore to Scale RL Training of LLMs on Hard Problems?

blog.ml.cmu.edu·11w

Carnegie Mellon University at EMNLP 2025

blog.ml.cmu.edu·14w

Learning from Failure to Tackle Extremely Hard Problems

blog.ml.cmu.edu·15w·

Discuss: Hacker News

Diffusion Beats Autoregressive in Data-Constrained Settings

blog.ml.cmu.edu·20w·

Discuss: Hacker News

Verlog: A Multi-turn RL framework for LLM agents

blog.ml.cmu.edu·21w

Carnegie Mellon University at ICML 2025

blog.ml.cmu.edu·31w

RLHF 101: A Technical Tutorial on Reinforcement Learning from Human Feedback

blog.ml.cmu.edu·36w

Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning

blog.ml.cmu.edu·38w

Carnegie Mellon University at ICLR 2025

blog.ml.cmu.edu·42w

Allie: A Human-Aligned Chess Bot

blog.ml.cmu.edu·42w

LLM Unlearning Benchmarks are Weak Measures of Progress

blog.ml.cmu.edu·43w

Copilot Arena: A Platform for Code

blog.ml.cmu.edu·44w

Optimizing LLM Test-Time Compute Involves Solving a Meta-RL Problem

blog.ml.cmu.edu·57w